研究人员开发了MOJO，一种用于脉冲标记神经数据模型的新型训练框架。MOJO通过掩码自编码将自监督学习与监督学习相结合，从而能够利用无标签数据。这种方法显著提高了解码性能，尤其是在数据稀疏的情况下，并且能够跨物种和神经模态（如人类皮层脑电图）进行泛化。 AI
影响 这项研究可能带来更灵活、可扩展的数据使用方式，用于训练神经基础模型，从而改进脑机接口。
排序理由 该集群包含一篇详细介绍神经数据解码新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.14086v1 Announce Type: new Abstract: Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pret…
Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding p…
Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding p…